跳到主要內容

臺灣博碩士論文加值系統

(3.229.142.104) 您好!臺灣時間:2021/07/30 15:04
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:鄭柏偉
研究生(外文):Po-Wei Cheng
論文名稱:應用旋轉梯度和粒子濾波技術即時偵測與追蹤人體
論文名稱(外文):Applying Rotation Gradient and Particle Filter Techniques to Real-Time Human Detection and Tracking
指導教授:黃有評黃有評引用關係
口試委員:朱鴻棋謝尚琳黃正民
口試日期:2012-07-11
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電機工程系研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:74
中文關鍵詞:人體追蹤粒子濾波器顏色直方圖旋轉梯度直方圖
外文關鍵詞:Human TrackingParticle FilterColor HistogramHOG
相關次數:
  • 被引用被引用:0
  • 點閱點閱:102
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著科技日新月異,人體偵測和追蹤已經成為熱門的研究領域,其應用範疇含蓋安全監控、智慧型運輸系統、居家照護等。但由於背景環境的複雜與多變,再加上行人的尺度大小和遮擋等問題,造成在實用上仍有許多值得改善之處。為了提升偵測和追蹤的效果,本論文提出一種使用旋轉梯度直方圖結合粒子濾波技術之方法,以達到即時的人體追蹤。偵測方式一般可分為背景建立、前景物擷取、背景更新三個階段,但在動態背景下這三個階段的設計會變的更加複雜。因此在偵測部分,採用旋轉梯度直方圖和支持向量機的方法將樣本訓練後,產生一個對人體的描述運算子,建立檢測器,之後再藉由檢測器偵測出在動態影像中可能的人體目標。在追蹤方面是使用粒子濾波技術,首先進行粒子取樣,建立運動模型,並選取顏色的分佈當作目標的特徵,接著計算目標和候選粒子之間的Bhattacharyya係數來給予權重,再使用加權平均估測出最後的目標位置。為了克服只使用單一顏色特徵來追蹤的缺點,本論文改良了粒子濾波器,加入邊緣特徵來提升追蹤的準確度。追蹤誤差採用最小均方根差來做比較。若僅考慮顏色特徵的追蹤誤差約74.18,但若加入邊緣特徵,則追蹤誤差可降至約61.84,此結果驗證所提系統具有較高的追蹤準確率和強健性。

With the advent of new technology and the innovation, human detection and tracking have become popular research topics. The scope of applications covers the security and surveillance, intelligent transportation systems, and home care systems. However, due to the complexity and changing background, people’s scale size, and occlusion problems, there are still limited practical applications. In order to improve the effect of detection and tracking, this study proposes a histogram oriented gradient method combined with particle filter to achieve real-time tracking of the human body. Detecting methods can be generally divided into three steps, namely, background construction, foreground subtracting and background updating. In reality, the design of those three stages is more complex in the dynamic environment. Therefore, we use histogram oriented gradient and support vector machine for training, building human descriptor in detection, and finding possible human in the films. Our tracking method uses particle filtering technique. We approach from particle sampling and then select color distribution as target feature. We find weights by computing Bhattacharyya coefficient between the target and candidate particles, and use the weighted average to estimate the final target location. We improve particle filter method by adding edge feature to overcome the shortcomings of using only one single color feature and achieve better tracking accuracy. The tracking error is compared by RMSE (root mean squared error). If only the color feature is considered, the tracking error is about 74.18. With the help of edge feature the error is reduced to approximately 61.84. Experimental results verify that the proposed system has higher tracking accuracy and is more robust.

摘 要 i
ABSTRACT ii
致 謝 iv
目 錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1研究背景 1
1.2研究目的 2
1.3研究方法 2
1.4論文架構 3
第二章 相關技術及運用探討 4
2.1 人體偵測 4
2.1.1 物體的特徵 4
2.1.2 偵測常用的方法 6
2.1.3 旋轉梯度特徵(Histogram of Oriented Gradient) 8
2.1.4 支持向量機 11
2.2 人體追蹤 16
2.2.1 剪影追蹤(Silhouette tracking) 16
2.2.2 核心追蹤(Kernel tracking) 17
2.2.3 點追蹤(Point tracking) 19
第三章 系統架構與設計 26
3.1 系統架構 26
3.1.1 硬體架構 26
3.1.2 軟體架構 28
3.2 偵測階段 28
3.3 LIBSVM 36
3.4 追蹤階段 37
3.5 開發平台 45
第四章 實驗結果與分析 46
4.1 實驗架構 46
4.2 人體偵測結果 46
4.3 人體追蹤結果 53
4.4 實驗分析結果 66
第五章 結論與未來展望 70
5.1 結論 70
5.2 未來展望 71
參考文獻 72


[1] 影像視訊科技未來展望與願景,http://bit.kuas.edu.tw/~cvgip10/IPPR20/09.pdf。
[2] Fast Texture Synthesis using Tree-structured Vector Quantization, http://graphics.stanford.edu/papers/texture-synthesis-sig00/texture.pdf.
[3] C. Harris an M. Stephens, “A combined corner and edge detector,” in Proc. of The 4th Alvey Vision Conf., Manchester, UK, pp.147-151, 1988.
[4] D. Lowe, “Distinctive image features from scale-invariant key point,” International Journal of Computer Vision, vol. 60, no. 2, pp.91-100, Jan. 2004.
[5] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Cambridge, MA, USA, vol. 2, pp.246-252, June 1999.
[6] M. Kass, A. Witkin and D. Terzopoulos, “Snakes: active contour models,” Int. Journal Computer Vision, vol. 1, pp.321-331, Jan. 1998.
[7] J.-Y. Gan, X.-H. Cao and J.-Y. Zeng, “Combining heritance adaBoost and random forests for face detection,” in Proc. of 9th IEEE Int. Conf. on Signal Processing (ICSP), Jiangmen, China, pp.666-669, Oct. 2010.
[8] Q. Tao, G.-W. Wu, F.-Y. Wang and J. Wang, “Posterior probability support vector machines for unbalanced data,” IEEE Trans. on Neural Networks, vol. 16, pp.1561-1573, Nov. 2005.
[9] J. S. Mashford, “A neural network image classification system for automatic inspection,” in Proc. of IEEE Int. Conf. on Neural Networks, Perth, WA, vo1. 2, pp.713-717, Nov./Dec. 1995.
[10] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, San Diego, CA, USA, vol. 1, pp.886-893, 2005.
[11] Finding People in Images and Video Sequences, http://lear.inrialpes.fr/people/dalal/NavneetDalalThesis.pdf.
[12] M.B. Kaaniche and F. Bremond, “Tracking hog descriptors for gesture recognition,” in Proc. of IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, Genova, Italy, pp.140-145, Sep. 2009.
[13] Z.-X. Chen, J. Wang and Z. Liquan, “Pedestrian detection based on the combination of hog and background subtraction method,” in Proc. of IEEE Int. Conf. on Transportation, Mechanical and Electrical Engineering, Changchun, Jilin, China, pp.527-533, Dec. 2011.
[14] H. Jung, J. K. Tan, S. Ishikawa and T. Morie, “Applying hog feature to the detection and tracking of a human on a bicycle,” in Proc. of IEEE Int. Conf. on Control, Automation and Systems, Gyeonggi-do, Korea, pp.1740-1743, Oct. 2011.
[15] C. Cortes and V. Vapnik, “Support vector networks,” Int. J. Machine Learning, vol. 20, pp.1-25, Feb. 1995.
[16] A. Yilmaz, O. Javed and M. Shah, “Object tracking: a survey,” ACM Computing Surveys, vol. 38, no. 4, pp.1-45, Dec. 2006.
[17] M. Kass, A. Witkin and D. Terzopoulos, “Snake: active contour models,” Int. J. Computer Vision, vol. 1, pp.321-331, Jan. 1988.
[18] D. Comaniciu, V. Ramesh and P. Meer, “ Real-time tracking of non-rigid objects using mean shift,” in Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, SC, vol. 2, pp.142-149, Sep. 2000.
[19] G. R. Bradski, “Computer video face tracking for use in a perceptual user interface,” Intel Technology Journal, vol. 2, pp.1-15, Aug. 1998.
[20] G. Welch and G. Bishop, An introduction to the Kalman filter, Department of Computer Science, University of North Carolina at Chapel Hill, pp.1-16, Apr. 2004.
[21] E. B. Meier and F. Ade, “Tracking cars in range images using the condensation algorithm,” in Proc. of Image Science Swiss Federal Institute of Technology (ETH), Tokyo, Japan, pp.129-134, Oct. 1999.
[22] F. Gustafsson, F. Gunnarsson,N. Bergman, U. Forssell, J. Jansson, R. Karlsson and P.-J. Nordlund, “Particle filters for positioning, navigation, and tracking,” IEEE Trans. on Signal Processing, vol. 2, pp.452-437, Feb. 2002.
[23] S. K. Zhou, R. Chellappa and B. Moghaddam, “Visual tracking and recognition using appearance-adaptive models in particle filters,” IEEE Trans. on Image Processing, vol. 13, pp.1491-1506, Nov. 2004.
[24] P. Pan and D. Schonfeld, “Video tracking based on sequential particle filtering on graphs,” IEEE Trans. on Image Processing, vol. 20, pp.1641-1651, June 2011.
[25] 數位攝影機,http://www.cdvideo.com.tw/SONY_HDD/SR220/sr220.html。
[26] 伽瑪校正,http://www.idsvision.com.tw/phpbb2/viewtopic.php?t=480。


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊